app.py

import gradio as gr
from modelscope.pipelines import pipeline
from modelscope.outputs import OutputKeys
from huggingface_hub import snapshot_download, HfApi
import pathlib

api = HfApi()
model_dir = pathlib.Path('weights')
snapshot_download('damo-vilab/modelscope-damo-text-to-video-synthesis',
                  repo_type='model', 
                  local_dir=model_dir, 
                  use_auth_token=True)

pipe = pipeline('text-to-video-synthesis', model_dir.as_posix())

def generate_video(prompt):
    output_video_path = pipe({'text': prompt})[OutputKeys.OUTPUT_VIDEO]
    return output_video_path

iface = gr.Interface(
    fn=generate_video,
    inputs=gr.Textbox(lines=2, placeholder="Enter your text prompt"),
    outputs="video")

iface.launch()